语义引导转换器网络用于高光谱图像中的作物分类
Weiqiang Pi1, Tao Zhang2, Rongyang Wang1
1College of Intelligent Manufacturing and Elevator, Huzhou Vocational and Technical College, Huzhou 313099, China.
Journal of imaging
|February 25, 2025
概括
一个新的语义引导变压器网络 (SGTN) 通过有效处理复杂的背景和多种规模的作物变异来改善高光谱作物分类. 这种先进的模型实现了高精度,为精准农业提供了更好的解决方案.
科学领域:
- 农业遥感 农业遥感
- 计算机视觉 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 超光谱遥感图像为作物监测提供了丰富的光谱信息.
- 现有的方法难以处理复杂的背景和不同的作物尺度,从而降低了分类准确性.
- 光谱相似性和尺度变化阻碍了高光谱作物分析中有效的特征提取.
研究的目的:
- 开发一个先进的深度学习模型,用于准确和强大的高光谱作物分类.
- 解决当前关于背景干扰和尺度变化的方法的局限性.
- 增强语义和空间光谱特征的提取,以改善作物识别.
主要方法:
- 提出了一个新的语义引导变压器网络 (SGTN).
- 一个多尺度空间光谱信息提取 (MSIE) 模块被设计用于处理尺度变化.
- 开发了一个语义引导注意 (SGA) 模块,以减少背景干扰,并专注于作物语义.
- 为了优化功能学习,采用了两阶段的特征提取结构.
主要成果:
- 在基准数据集上,SGTN实现了高整体准确度:98.24% (印度松树),98.34% (帕维亚大学) 和97.89% (萨利纳斯).
- 与现有方法相比,该模型显示出更高的分类准确性和概括性能.
- MSIE和SGA模块有效地改善了特征提取和减少背景噪声.
结论:
- SGTN有效地克服了传统的深度学习方法对高光谱作物分类的局限性.
- 拟议的模型在具有挑战性的遥感场景中提供了更高的准确性和稳定性.
- 该SGTN显示了未来精准农业应用的潜力,包括疾病检测和产量预测.
相关概念视频
02:16Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
02:35Key Elements for Plant Nutrition
18.6K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.6K